Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbered lists, phases, or sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fundada
    1.07
     mislead
    1.00
     ninguna
    0.99
     consecuencias
    0.96
     beob
    0.95
     cumplimiento
    0.95
     McA
    0.95
     beobachten
    0.95
     bezahlen
    0.95
     cuestion
    0.94
    POSITIVE LOGITS
    ти
    0.97
    мо
    0.93
    delicious
    0.86
    champion
    0.85
    er
    0.84
    ри
    0.84
     delicious
    0.83
    ман
    0.83
    чо
    0.82
    Tham
    0.81
    Act Density 0.000%

    No Known Activations